Sandbox vectors

Let’s define some vectors which can be used for demonstrations:

manyNumbers <- sample( 1:1000, 20 )
manyNumbers
 [1] 751 135  33 146 326 298 394 913 605 155 169 168 348 360 392  29 258 935 299  67
manyNumbersWithNA <- sample( c( NA, NA, NA, manyNumbers ) )
manyNumbersWithNA
 [1]  NA  67 146 258 135 751 326 168  NA 605 360 913 392 348 298  NA  29 299 935 169 394 155  33
duplicatedNumbers <- sample( 1:5, 10, replace = TRUE )
duplicatedNumbers
 [1] 3 1 4 1 5 4 2 2 3 5
letters
 [1] "a" "b" "c" "d" "e" "f" "g" "h" "i" "j" "k" "l" "m" "n" "o" "p" "q" "r" "s" "t" "u" "v" "w" "x" "y"
[26] "z"
LETTERS
 [1] "A" "B" "C" "D" "E" "F" "G" "H" "I" "J" "K" "L" "M" "N" "O" "P" "Q" "R" "S" "T" "U" "V" "W" "X" "Y"
[26] "Z"
mixedLetters <- c( sample( letters, 5 ), sample( LETTERS, 5 ) )
mixedLetters
 [1] "x" "u" "o" "v" "y" "D" "S" "Y" "Q" "T"

Are all/any elements TRUE

  • Input: logical vector
  • Output: single logical value
  • Task: try, understand what happens when you use manyNumbersWithNA instead of manyNumbers.
all( manyNumbers <= 1000 )
[1] TRUE
all( manyNumbers <= 500 )
[1] FALSE
any( manyNumbers > 1000 )
[1] FALSE
any( manyNumbers > 500 )
[1] TRUE
all( !is.na( manyNumbers ) )
[1] TRUE
any( is.na( manyNumbers ) )
[1] FALSE

Which elements are TRUE

Input: logical vector Output: vector of numbers (positions)

which( manyNumbers > 900 )
[1]  8 18
which( manyNumbersWithNA > 900 )
[1] 12 19
which( is.na( manyNumbersWithNA ) )
[1]  1  9 16

Filtering vector elements

  • Input: any vector and filtering condition
  • Output: elements of the input vector
  • Note: several ways to get the same effect
manyNumbers[ manyNumbers > 900 ] # indexing by logical vector
[1] 913 935
manyNumbers[ which( manyNumbers > 900 ) ] # indexing by positions
[1] 913 935
somePositions <- which( manyNumbers > 900 )
manyNumbers[ somePositions ]
[1] 913 935

Are some elements among other elements

  • Input: two vectors
  • Output: a logical vector corresponding to the first input vector
"A" %in% LETTERS
[1] TRUE
c( "X", "Y", "Z" ) %in% LETTERS
[1] TRUE TRUE TRUE
all( c( "X", "Y", "Z" ) %in% LETTERS )
[1] TRUE
all( mixedLetters %in% LETTERS )
[1] FALSE
any( mixedLetters %in% LETTERS )
[1] TRUE
mixedLetters[ mixedLetters %in% LETTERS ]
[1] "D" "S" "Y" "Q" "T"
mixedLetters[ !( mixedLetters %in% LETTERS ) ]
[1] "x" "u" "o" "v" "y"
manyNumbers %in% 300:600
 [1] FALSE FALSE FALSE FALSE  TRUE FALSE  TRUE FALSE FALSE FALSE FALSE FALSE  TRUE  TRUE  TRUE FALSE FALSE
[18] FALSE FALSE FALSE
which( manyNumbers %in% 300:600 )
[1]  5  7 13 14 15
sum( manyNumbers %in% 300:600 )
[1] 5

Pick one of two (three) depending on condition

  • Input: a logical vector and two vectors additional vectors (for TRUE, for FALSE)
  • Output: elements of the additional vectors
  • Note: it can take care of NAs
if_else( manyNumbersWithNA >= 500, "large", "small" )
 [1] NA      "small" "small" "small" "small" "large" "small" "small" NA      "large" "small" "large"
[13] "small" "small" "small" NA      "small" "small" "large" "small" "small" "small" "small"
if_else( manyNumbersWithNA >= 500, "large", "small", "UNKNOWN" )
 [1] "UNKNOWN" "small"   "small"   "small"   "small"   "large"   "small"   "small"   "UNKNOWN" "large"  
[11] "small"   "large"   "small"   "small"   "small"   "UNKNOWN" "small"   "small"   "large"   "small"  
[21] "small"   "small"   "small"  
# here integer 0L is needed instead of real 0.0 
# manyNumbersWithNA contains integer numbers and the method complains
if_else( manyNumbersWithNA >= 500, manyNumbersWithNA, 0L ) 
 [1]  NA   0   0   0   0 751   0   0  NA 605   0 913   0   0   0  NA   0   0 935   0   0   0   0

Duplicates and unique elements

  • Input: a vector
unique( duplicatedNumbers )
[1] 3 1 4 5 2
unique( c( NA, duplicatedNumbers, NA ) )
[1] NA  3  1  4  5  2
duplicated( duplicatedNumbers )
 [1] FALSE FALSE FALSE  TRUE FALSE  TRUE FALSE  TRUE  TRUE  TRUE

Positions of max/min elements

which.max( manyNumbersWithNA )
[1] 19
manyNumbersWithNA[ which.max( manyNumbersWithNA ) ]
[1] 935
which.min( manyNumbersWithNA )
[1] 17
manyNumbersWithNA[ which.min( manyNumbersWithNA ) ]
[1] 29
range( manyNumbersWithNA, na.rm = TRUE )
[1]  29 935

Sorting/ordering of vectors

manyNumbersWithNA
 [1]  NA  67 146 258 135 751 326 168  NA 605 360 913 392 348 298  NA  29 299 935 169 394 155  33
sort( manyNumbersWithNA )
 [1]  29  33  67 135 146 155 168 169 258 298 299 326 348 360 392 394 605 751 913 935
sort( manyNumbersWithNA, na.last = TRUE )
 [1]  29  33  67 135 146 155 168 169 258 298 299 326 348 360 392 394 605 751 913 935  NA  NA  NA
sort( manyNumbersWithNA, na.last = TRUE, decreasing = TRUE )
 [1] 935 913 751 605 394 392 360 348 326 299 298 258 169 168 155 146 135  67  33  29  NA  NA  NA
manyNumbersWithNA[1:5]
[1]  NA  67 146 258 135
order( manyNumbersWithNA[1:5] )
[1] 2 5 3 4 1
rank( manyNumbersWithNA[1:5] )
[1] 5 1 3 4 2
sort( mixedLetters )
 [1] "D" "o" "Q" "S" "T" "u" "v" "x" "y" "Y"

Ranking of vectors

manyDuplicates <- sample( 10:15, 10, replace = TRUE )
rank( manyDuplicates )
 [1]  7.0  1.5  7.0  7.0 10.0  7.0  4.0  7.0  3.0  1.5
rank( manyDuplicates, ties.method = "min" )
 [1]  5  1  5  5 10  5  4  5  3  1
rank( manyDuplicates, ties.method = "random" )
 [1]  7  1  6  9 10  8  4  5  3  2

Rounding numbers

v <- c( -1, -0.5, 0, 0.5, 1, rnorm( 10 ) )
v
 [1] -1.00000000 -0.50000000  0.00000000  0.50000000  1.00000000 -0.10812308 -2.28714919 -0.04818282
 [9] -0.35614287  0.99657785 -0.05962949 -1.10161884 -0.78380958 -1.57000720 -2.32641992
round( v, 0 )
 [1] -1  0  0  0  1  0 -2  0  0  1  0 -1 -1 -2 -2
round( v, 1 )
 [1] -1.0 -0.5  0.0  0.5  1.0 -0.1 -2.3  0.0 -0.4  1.0 -0.1 -1.1 -0.8 -1.6 -2.3
round( v, 2 )
 [1] -1.00 -0.50  0.00  0.50  1.00 -0.11 -2.29 -0.05 -0.36  1.00 -0.06 -1.10 -0.78 -1.57 -2.33
floor( v )
 [1] -1 -1  0  0  1 -1 -3 -1 -1  0 -1 -2 -1 -2 -3
ceiling( v )
 [1] -1  0  0  1  1  0 -2  0  0  1  0 -1  0 -1 -2

Naming vector elements

heights <- c( Amy = 166, Eve = 170, Bob = 177 )
heights
Amy Eve Bob 
166 170 177 
names( heights )
[1] "Amy" "Eve" "Bob"
names( heights ) <- c( "AMY", "EVE", "BOB" )
heights
AMY EVE BOB 
166 170 177 
heights[[ "EVE" ]]
[1] 170

Generating grids

expand_grid( x = c( 1:3, NA ), y = c( "a", "b" ) )
# A tibble: 8 × 2
      x y    
  <int> <chr>
1     1 a    
2     1 b    
3     2 a    
4     2 b    
5     3 a    
6     3 b    
7    NA a    
8    NA b    

Generating combinations

combn( c( "a", "b", "c", "d", "e" ), m = 2, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  "c"  "d"  
[2,] "b"  "c"  "d"  "e"  "c"  "d"  "e"  "d"  "e"  "e"  
combn( c( "a", "b", "c", "d", "e" ), m = 3, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  
[2,] "b"  "b"  "b"  "c"  "c"  "d"  "c"  "c"  "d"  "d"  
[3,] "c"  "d"  "e"  "d"  "e"  "e"  "d"  "e"  "e"  "e"  


Copyright © 2021 Biomedical Data Sciences (BDS) | LUMC